POSTER P418: Towards using GANs in astrophysical Monte-Carlo simulations

ADASS posters are displayed all week

When

11:18 p.m., Nov. 7, 2023

Theme: AI in Astronomy

pretalxeposter

Accurate modeling of spectra produced by the X-ray sources requires use of Monte-Carlo simulations. These simulations need to evaluate physical processes, such as those occurring in accretion processes around compact objects by sampling a number of different probability distributions. This is computationally time-consuming and could be sped up if replaced by neural networks. We demonstrate, on an example of the Maxwell-Juttner distribution that describes the speed of relativistic electrons, that the generative adversarial network (GAN) is capable of statistically replicating the distribution. The average value of the Kolmogorov-Smirnov test is 0.5 for samples generated by the neural network, showing that the generated distribution cannot be distinguished from the true distribution.

Contacts

Karel Adamek, University of Oxford